powerplan
An MCP server that gives agents a human-language API over PLAN.md, enabling project plan management, task tracking, and iteration lifecycle without direct file editing.
README
powerplan
PLAN.md as the operational backbone of agentic development.
powerplan is a standalone MCP server that
gives coordinators and worker agents a human-language API over your
project’s PLAN.md: show progress, create iterations, complete tasks, keep the
header truthful — without freeform file thrash.
| Server name | powerplan |
| Status | v0.2.2 — create_plan, mutations, lifecycle, check_plan (PLAN.md) |
| PRD | PRD.md |
| Site | GitHub Pages |
| Pairs with | PowerSpawn (optional submodule) |
Why
Agents often edit PLAN.md by hand. Headers drift, “COMPLETE” gets stamped
without proof, and multi-agent swarms step on each other. powerplan is the
single writer: tolerant reader, surgical writer, optional [agent: …] tags.
Install
Option A — clone + editable install
git clone https://github.com/CynaCons/powerplan.git
cd powerplan
pip install -e ".[dev]"
Option B — via PowerSpawn (submodule)
Projects that already use PowerSpawn can pull powerplan automatically:
git submodule update --init --recursive # if PowerSpawn vendors powerplan/
Then point MCP at powerplan/powerplan_server.py or python -m powerplan
with PYTHONPATH including the submodule root.
Option C — path-only (no install)
python /path/to/powerplan/powerplan_server.py
MCP registration
Claude Code / project .mcp.json
{
"mcpServers": {
"powerplan": {
"command": "python",
"args": ["-m", "powerplan"],
"env": {
"PYTHONIOENCODING": "utf-8",
"PYTHONUNBUFFERED": "1"
}
}
}
}
Grok (~/.grok/config.toml or project config)
[mcp_servers.powerplan]
command = "python"
args = ["-m", "powerplan"]
env = { PYTHONUNBUFFERED = "1" }
enabled = true
Alongside PowerSpawn
{
"mcpServers": {
"powerplan": {
"command": "python",
"args": ["-m", "powerplan"]
},
"powerspawn": {
"command": "python",
"args": ["-m", "powerspawn.mcp_server"]
}
}
}
Register both as separate servers — nesting in a monorepo does not merge MCPs.
Tools (v0.2.2)
Every tool accepts optional plan_path (relative or absolute). Default: walk
up from cwd to the nearest PLAN.md.
| Tool | Behavior |
|---|---|
create_plan |
Bootstrap ./PLAN.md (or plan_path) when missing; force to overwrite |
get_current_iteration |
Preferred for agents — scoped JSON for current work |
get_iteration |
JSON for one version (tasks, progress) |
list_iterations / find_task / get_backlog |
Navigate without full-file reads |
create_major / create_iteration / add_task / … |
Surgical mutations |
complete_task / reopen_task |
Checkbox updates; optional [agent: id] |
start_iteration / close_iteration |
ACTIVE/current vs COMPLETE lifecycle |
check_plan |
Structure lint |
show_plan / show_current_iteration |
Compact human skim (not a full dump) |
Agent rule: prefer get_current_iteration / get_iteration over reading all of PLAN.md.
If no plan exists → create_plan first.
Managed plan format
| Construct | Pattern |
|---|---|
| Major | ## vX.Y — Title |
| Iteration | ### vX.Y.Z — Title |
| Goal | **Goal:** … |
| Tasks | - [ ] / - [x] |
| Backlog | ## Backlog |
Phase-like headers and other prose are preserved as opaque blocks (tolerant reader). See PRD for principles (single writer, no evidence journal in the tool).
Development
pip install -e ".[dev]"
pytest -q
python -m powerplan # stdio MCP (use with an MCP client)
Landing page:
cd site && npm ci && npm run dev
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.